Category Archives: Probabilities
A Must-Have Book for Every Test Engineer
The Test Engineer’s Measurement Handbook / How to Design Tests for 1st-Pass Success
by Van Brollini
Van Brollini’s new book is an essential addition to the test engineer’s library, as well as the library of any product manager.
The Handbook contains practical advice that is based on Mr. Brollini’s extensive experience with test development, including unique insights that I have not seen elsewhere, insights that will provide the test engineer with a quantum leap in productivity.
The test engineer will also appreciate the fact that Brollini’s methods — clearly presented as a series of rules, tips, and straightforward equations — are practical and cost-effective, illustrated by real-world examples throughout.
The Handbook’s teachings can be applied with basic math and spreadsheet tools, although Brollini does recommend Design Master™ for best efficiency, particularly for more advanced applications.
(I have known Van for many years, as he was one of the first engineers to adopt our Design Master software. From time to time he has offered suggestions for improvements, which were incorporated into the software.)
The Test Engineer’s Measurement Handbook is available through the DACI website.
-Ed Walker
3rd Qtr 2011
(c) 2011 Design/Analysis Consultants, Inc.
Newsletter content may be copied in whole or part if attribution
to DACI and any referenced source is prominently displayed with the copied material
This Issue: NEWS BITE: Mutant Singing Cantaloup Wins Karaoke Contest! / MORE UNINTENDED CONSEQUENCES: Hands-Free Faucets / DESIGN MASTER TIP: AC Rectifier Worst Case Analysis Made Easy / ART MEETS ENGINEERING: The Invisible Man / STATISTICAL DESIGN PITFALLS: Monte Carlo Is Not Worst Case Analysis
NEWS BITE: Mutant Singing Cantaloup Wins Karaoke Contest!
“Freaky Robot Mouth Learns to Sing,”
Evan Ackerman, 13 July 2011, IEEE Spectrum
MORE UNINTENDED CONSEQUENCES: Hands-Free Faucets Harbor More Germs Than Standard Faucets
Details here.
DESIGN MASTER™ TIP: AC Rectifier Circuit Worst Case Analysis Made Easy
In our previous Newsletter we provided a pretty good estimate for the ripple current for the bulk capacitor in an AC rectifier circuit. But what if you have a large volume product and you need a full worst case analysis to ensure high reliability, but one that is not overly pessimistic so that you can minimize cost? Design Master can help you achieve that optimum balance.
As readers are aware, we’ve started to release some DMeXpert™ “fill in the blank” WCA templates to make the design engineer’s life a bit easier. One of these is our AC Bridge Rectifier Analysis (ACBR1 $19) which allows the designer to determine all of the worst case component stresses within a minute or two. The analysis includes the effects of source impedance Rs (such as transformer secondary winding ohms), which if present can be used to reduce capacitor ripple current requirements, hence reduce capacitor cost.
As those who have studied AC rectifier circuits are aware, this seemingly simple circuit has resisted for decades all of the attempts to generate a single-formula solution, until recently, which we’ve included in ACBR1. Based on Keng Wu’s article, “Analyzing Full-Wave Rectifiers With Capacitor Filters” (1 Jan 2010, Power Electronics Technology), Wu’s formula allows a straightforward circuit solution, greatly reducing computational time. So with ACBR1 you can just fill in the blanks, click Calculate, and let Design Master do the rest.
ART MEETS ENGINEERING: The Invisible Man
Engineers who work for the military are sometimes required to design clothing, equipment, or even entire shelters to be “invisible” to various detection means. Chinese artist Liu Bolin has a gift for applying such camouflage in a non-technological way, as seen below. Hint: If you can’t spot Liu, look for his shoes first.
From “The Invisible Man: Dragon Series,” Vurdlak, 28 June 2011, http://www.moillusions.com
Some more fascinating photos here and here.
STATISTICAL DESIGN PITFALLS: Monte Carlo Is Not Worst Case Analysis
A lot of folks like to let a simulator crank out “worst case” results, using Monte Carlo statistical methods. But as we’ve explained previously (“Design Master vs Extreme Value, RSS, Monte Carlo, & Simulation,” and “Design Master vs Monte Carlo“), this can be not only time consuming, but risky. For example, Monte Carlo can easily miss small but significant errors (see example below). In addition, if the Monte Carlo runs are improperly implemented (such as including temperature or other dynamic variables) you will likely obtain wildly inaccurate results.
The Design Master Advantage
Instead of statistical sampling, Design Master uses a top-down approach to achieve safer and more cost-effective results, by (a) detecting the extreme limits of performance, and then (b) using a proprietary probability algorithm to estimate how often those results will exceed the specification limits.
EXAMPLE
Design Master results at 2 samples/variable versus
Monte Carlo at 10,000 samples/variable, for the gain of an 8-variable filter
As can be seen, the Monte Carlo analysis detected a minimum of 8.42 versus the actual minimum of 7.86, a 7% error, and a maximum of 16.0 versus the actual maximum of 18.8, a 15% error.
4th Qtr 2010
(C) 2010 Design/Analysis Consultants, Inc.
Newsletter content may be copied in whole or part if attribution
to DACI and any referenced source is prominently displayed with the copied material
This Issue: NEWS BITE: Reporters Scramble To Adapt To Cameramen Layoffs During Economic Downturn! / DM V8 And DMX Released / REVIEW: The Social Network: Entertaining But Not True / NEWS BULLETS: Unintended Consequences (Reusable Grocery Bags) / RECREATION: Having Fun With Fantasy Football
NEWS BITE: Reporters Scramble To Adapt To Cameramen Layoffs During Economic Downturn!
.
.
.
.
.
.
Teleactor Annamarie Ho. Photo: Bart Nagel
“Q&A: Ken Goldberg Discusses Telerobots, Androids, and Heidegger,” by Erico Guizzo, IEEE Spectrum, 1 Oct 2010
DESIGN MASTER: DM V8 with DMeXpert™ (DMX) Released
DMX provides expertly-designed “fill in the blanks” templates for thorough and efficient worst case analysis. Click here for details. If you purchased Design Master on or after October 4 2009, you can obtain an update at no charge; please contact us for download instructions (new install required for V8).
REVIEW: The Social Network: Entertaining But Not True
“Mark Zuckerberg, Facebook’s young and intrepid creator, is portrayed as a geek who starts his path to dot com glory after getting dumped by a girl … If it were true it would be a lot more compelling. Back in 2005 and 2006, shortly after the film is set, I interviewed Zuckerberg on several occasions, and he wasn’t much like the guy on-screen. In addition to actually having a girlfriend, a fact left conveniently out of the film, he had a lot of thoughtful things to say about the world he was creating online. ”
“The Social Network’s Science Fiction,” by David Kushner, IEEE Spectrum, 7 Oct 2010
The Bozo Award is presented to screenwriter Aaron Sorkin and the movie’s producers for their lack of integrity, as demonstrated by their willingness to damage reputations through false representations of actual events.
NEWS BULLETS: Unintended Consequences Strike Again
“The CALL7 Investigators tested several reusable bags used by 7NEWS colleagues and another from a woman going into a Denver grocery store. Marchetta took the lab results to Dr. Michelle Barron, the infectious disease expert at the University of Colorado Hospital. ‘Wow. Wow. That is pretty impressive,’ said Barron. Barron examines lab results for a living. ‘Oh my goodness! This is definitely the highest count,’ Barron commented while looking at the bacteria count numbers.”
-“Reusable Grocery Bags Breed Bacteria” By Theresa Marchetta, 28 Sep 2010 Denver News
RECREATION: Having Fun with Statistics and Fantasy Football
Design Master™ is used by engineers to help create highly reliable products, but it has been suggested to us that it can be used for some fun, too, such as fantasy football or other games that use statistics. It might even provide a bit of an edge, because its probability models provide more information than simple statistical averages.
For example, you can define a group of players in the Variables Library, enter the raw stats for each player, and let Design Master generate their “player strength” probability models (Tools/Make A Model From Raw Data).
In the worksheet, you create a simple Team formula that defines the strength of the team, using a weighted sum of all the players —
TeamA = 0.2*Player1 + 0.10*Player2 + 0.15*Player3 + …
— where the weights add to 1.0 (100%).
Then press Calculate to generate the team’s probability model.
Repeat this for a competing TeamB and its players, and then compare the team models:
TeamA strength = 5 to 10 TeamB strength = 4 to 16
There are many ways to make a comparison, but a simple way would be just to subtract the teams. For example, to determine the probability of TeamA losing to TeamB,
TeamAWin = TeamA – TeamB
where the minimum limit is set to zero (i.e. the case where TeamA is less strong than TeamB).
Probability models help guard against counter-intuitive bets. In this example, it may appear that TeamB (max strength of 16) is superior to TeamA (max strength of 10). But if you look at average strengths, TeamA comes out on top (8 to 7). How should these factors be evaluated?
Press calculate, and the resultant probability distribution indicates that the “weakling” Team A only has about a 12% chance of losing to TeamB:
Furthermore, knowing the actual probability of 12% provides an added edge for intelligent odds-making … all in fun, of course.
Q&A: Ken Goldberg Discusses Telerobots, Androids, and Heidegger
3rd Qtr 2010
(C) 2010 Design/Analysis Consultants, Inc.
Newsletter content may be copied in whole or part if attribution
to DACI and any referenced source is prominently displayed with the copied material
This Issue: NEWS BITE: Man Shocked To Discover Twin Brother Is A Robot! / DM V8 Wish List / NEWS BULLETS: Unintended Consequences Strike Again / DACI’s BLOG: An Engineer Writes A Novel / KEEPING OUT OF TROUBLE: What Every Engineer Should Know About Statistics / OUR VIEW: Using Statistics For High-Quality Designs
NEWS BITE: Man Shocked To Discover Twin Brother Is A Robot!
.
.
.
“The Amazing Androids of Hiroshi Ishiguro” from “Special Report: Robots for Real,” IEEE Spectrum
DM V8 Wish List
Design MasterTM V8 (Major Upgrade) is planned for release soon, so now’s your chance to send us any suggestions for features you would like to see added. Also, if you have the current version of DM and would like to receive a beta version of V8, please let us know.
For more details on the current version, please click here: Design Master V7
NEWS BULLETS: Unintended Consequences Strike Again
“Rear-end collisions more than doubled and accidents increased overall in the first 70 days of red-light cameras in West Palm Beach compared to the same period of 2009, traffic records reviewed by The Palm Beach Post show.”
.
-“Rear-end collisions jump at red-light camera intersections in West Palm Beach” By Charles Elmore, 15 July 2010 Palm Beach Post
DACI’s BLOG: An Engineer Writes A Novel
Think you can figure out what’s happening? Unconventional, but logically consistent. Read about Nexus here.
Update: NEXUS receives “highly recommended” rating from Cindy Taylor, Allbooks Review. Read the full review here.
.
KEEPING OUT OF TROUBLE: What Every Engineer Should Know About Statistics
“Supposedly, the proper use of statistics makes relying on scientific results a safe bet. But in practice, widespread misuse of statistical methods makes science more like a crapshoot…”
“It’s science’s dirtiest secret: The ‘scientific method’ of testing hypotheses by statistical analysis stands on a flimsy foundation. Statistical tests are supposed to guide scientists in judging whether an experimental result reflects some real effect or is merely a random fluke, but the standard methods mix mutually inconsistent philosophies and offer no meaningful basis for making such decisions. Even when performed correctly, statistical tests are widely misunderstood and frequently misinterpreted. As a result, countless conclusions in the scientific literature are erroneous, and tests of medical dangers or treatments are often contradictory and confusing.”
-from “Odds Are, It’s Wrong / Science fails to face the shortcomings of statistics” By Tom Siegfried, 27 March 2010 Science News
OUR VIEW: Using Statistics For Achieving High-Quality Designs
We have long recommended that statistical inference (limited sampling) not be used to try to predict performance (a practice that leads to the myriad problems discussed in the article referenced above), and have recommended instead that known performance limits and sensitivities be used to estimate the probability of success.
Stated another way, statistics (properly employed) can provide a good description of observed performance; it cannot be used to predict non-observed performance.
Example: If one examines all of the socks of various colors in a large drawer, one can use that data (analogous to a part vendor’s data sheet) to estimate the probability of blindly pulling out a sock of a certain color. For instance, if there are a few purple socks (unacceptable performance), we know the odds of getting that color.
However, if one only examines a few of the socks (limited experimental data, or a data sheet that only provides “typical” values), one cannot reliably predict much of anything. Such limited data is therefore unsuitable for high-quality designs.
In our consulting practice we have observed more than once the natural but very risky tendency of a design team to “see” hoped-for performance from limited experimental results, sometimes leading to premature jubilation. As the team’s official party-pooper, we have always advised keeping the champagne corked until sufficient data have been accumulated to be sure that the performance is properly understood. In every case this advice has served our customers well.
